对齐与安全论文趋势 2023–2026

主要结论

• 对齐与安全论文从 2023 年的 438 篇增长到 2026 年的 1,882 篇，三年间扩大到约 4.3 倍。
• NeurIPS 是发对齐与安全论文最多的会议，2023–2026 年共 1,421 篇，占四个会议总量的 31%。
• 交叉方向里涨得最快的是社会层面 · safety：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 137 篇。
• 在「对齐与负责任 AI」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的社会层面 · safety是 93 倍，对齐与安全是 4.3 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026$\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
• ICML 2026AICrypto: Evaluating Cryptography Capabilities of Large Language Models
• ICLR 2026A Fair Bayesian Inference through Matched Gibbs Posterior
• CVPR 2026Advancing Cancer Prognosis with Hierarchical Fusion of Genomic Proteomic and
• NeurIPS 2025$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
• ICML 2025A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
• ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
• CVPR 2025AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models
• NeurIPS 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
• ICML 2024A Global Geometric Analysis of Maximal Coding Rate Reduction
• ICLR 2024A unique M-pattern for micro-expression spotting in long videos
• CVPR 2024Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
• NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
• ICML 2023A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks
• ICLR 2023Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
• CVPR 2023Adjustment and Alignment for Unbiased Open Set Domain Adaptation
• NeurIPS 2026$\mathcal{P}$Torch: Narrowing the Gap Between Projection and Gradient-Based Learning
• ICML 2026Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
• ICLR 2026A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
• CVPR 2026AlignPose Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment

全部对齐与安全论文

共 1,421 篇，第 13 / 29 页

601. NeurIPS 2025Doubly Robust Alignment for Large Language Models
602. NeurIPS 2025DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
603. NeurIPS 2025DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving
604. NeurIPS 2025DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
605. NeurIPS 2025Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts
606. NeurIPS 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
607. NeurIPS 2025DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
608. NeurIPS 2025Dynamic Diameter in High-Dimensions against Adaptive Adversary and Beyond
609. NeurIPS 2025Dynamic Risk Assessments for Offensive Cybersecurity Agents
610. NeurIPS 2025Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks
611. NeurIPS 2025Efficient and Generalizable Mixed-Precision Quantization via Topological Entropy
612. NeurIPS 2025Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles
613. NeurIPS 2025Efficient Preference-Based Reinforcement Learning: Randomized Exploration meets Experimental Design
614. NeurIPS 2025Elastic Robust Unlearning of Specific Knowledge in Large Language Models
615. NeurIPS 2025ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
616. NeurIPS 2025Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems
617. NeurIPS 2025Enhancing CLIP Robustness via Cross-Modality Alignment
618. NeurIPS 2025Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
619. NeurIPS 2025Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization
620. NeurIPS 2025EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
621. NeurIPS 2025Erasing Conceptual Knowledge from Language Models
622. NeurIPS 2025Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism
623. NeurIPS 2025ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space
624. NeurIPS 2025ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality
625. NeurIPS 2025EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
626. NeurIPS 2025Explainable Reinforcement Learning from Human Feedback to Improve Alignment
627. NeurIPS 2025Explaining and Mitigating Crosslingual Tokenizer Inequities
628. NeurIPS 2025Explaining the Law of Supply and Demand via Online Learning
629. NeurIPS 2025Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback
630. NeurIPS 2025Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning
631. NeurIPS 2025Failure Prediction at Runtime for Generative Robot Policies
632. NeurIPS 2025Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity
633. NeurIPS 2025Fast Computation and Optimization for Opinion-Based Quantities of Friedkin-Johnsen Model
634. NeurIPS 2025FastJAM: a Fast Joint Alignment Model for Images
635. NeurIPS 2025FedFree: Breaking Knowledge-sharing Barriers through Layer-wise Alignment in Heterogeneous Federated Learning
636. NeurIPS 2025FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization
637. NeurIPS 2025Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
638. NeurIPS 2025Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
639. NeurIPS 2025Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
640. NeurIPS 2025Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360° Firefighting Video
641. NeurIPS 2025FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing
642. NeurIPS 2025FraPPE: Fast and Efficient Preference-Based Pure Exploration
643. NeurIPS 2025From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
644. NeurIPS 2025From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
645. NeurIPS 2025Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
646. NeurIPS 2025GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
647. NeurIPS 2025Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
648. NeurIPS 2025Generalizing while preserving monotonicity in comparison-based preference learning models
649. NeurIPS 2025Generative RLHF-V: Learning Principles from Multi-modal Human Preference
650. NeurIPS 2025GMV: A Unified and Efficient Graph Multi-View Learning Framework

常见问题

2023–2026 年四大会议一共有多少篇对齐与安全论文？

共 4,558 篇，按年份分别是 2023 年 438 篇、2024 年 875 篇、2025 年 1,363 篇、2026 年 1,882 篇。

NeurIPS 2026 有多少篇对齐与安全论文？

NeurIPS 2026 有 480 篇对齐与安全论文，上一届是 455 篇。

ICLR 2026 有多少篇对齐与安全论文？

ICLR 2026 有 623 篇对齐与安全论文，上一届是 473 篇。

ICML 2026 有多少篇对齐与安全论文？

ICML 2026 有 551 篇对齐与安全论文，上一届是 300 篇。

CVPR 2026 有多少篇对齐与安全论文？

CVPR 2026 有 228 篇对齐与安全论文，上一届是 135 篇。

哪个会议的对齐与安全论文最多？

NeurIPS，2023–2026 年共 1,421 篇。